Parkinson's Disease Data Classification Using Evolvable Wavelet Neural Networks

Parkinson's Disease is the second most common neurological condition in Australia. This paper develops and compares a new type of Wavelet Neural Network that is evolved via Cartesian Genetic Programming for classifying Parkinson's Disease data based on speech signals. The classifier is trained using 10-fold and leave-one-subject-out cross validation testing strategies. The results indicate that the proposed algorithm can find high quality solutions and the associated features without requiring a separate feature pruning pre-processing step. The technique aims to become part of a future support tool for specialists in the early diagnosis of the disease reducing misdiagnosis and cost of treatment.

[1]  Achilleas Zapranis,et al.  Wavelet Neural Networks: A Practical Guide , 2011, Neural Networks.

[2]  Gul Muhammad Khan,et al.  Efficient representation of Recurrent Neural Networks for markovian/non-markovian non-linear control problems , 2010, 2010 10th International Conference on Intelligent Systems Design and Applications.

[3]  João Paulo Papa,et al.  Improving Parkinson's disease identification through evolutionary-based feature selection , 2011, 2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[4]  Julian Francis Miller,et al.  Cartesian genetic programming , 2000, GECCO '10.

[5]  Max A. Little,et al.  Suitability of Dysphonia Measurements for Telemonitoring of Parkinson's Disease , 2008, IEEE Transactions on Biomedical Engineering.

[6]  Julian F. Miller,et al.  What bloat? Cartesian Genetic Programming on Boolean problems , 2003 .

[7]  Julian Francis Miller,et al.  Neutrality and the Evolvability of Boolean Function Landscape , 2001, EuroGP.

[8]  Gul Muhammad Khan,et al.  Fast learning neural networks using Cartesian genetic programming , 2013, Neurocomputing.

[9]  Julian Francis Miller,et al.  Predicting Prime Numbers Using Cartesian Genetic Programming , 2007, EuroGP.

[10]  Julian Francis Miller,et al.  Solving real-valued optimisation problems using cartesian genetic programming , 2007, GECCO '07.

[11]  Julian Francis Miller,et al.  The Advantages of Landscape Neutrality in Digital Circuit Evolution , 2000, ICES.

[12]  Olcay Kursun,et al.  Telediagnosis of Parkinson’s Disease Using Measurements of Dysphonia , 2010, Journal of Medical Systems.

[13]  Hans-Paul Schwefel,et al.  Evolution strategies – A comprehensive introduction , 2002, Natural Computing.

[14]  Stephan K. Chalup,et al.  Evolving Wavelet Neural Networks for Breast Cancer Classi cation , 2014, AusDM.

[15]  Resul Das,et al.  A comparison of multiple classification methods for diagnosis of Parkinson disease , 2010, Expert Syst. Appl..

[16]  Kemal Polat,et al.  Classification of Parkinson's disease using feature weighting method on the basis of fuzzy C-means clustering , 2012, Int. J. Syst. Sci..

[17]  Max A. Little,et al.  Exploiting Nonlinear Recurrence and Fractal Scaling Properties for Voice Disorder Detection , 2007, Biomedical engineering online.

[18]  Gang Wang,et al.  An efficient diagnosis system for detection of Parkinson's disease using fuzzy k-nearest neighbor approach , 2013, Expert Syst. Appl..

[19]  Julian Francis Miller,et al.  Finding Needles in Haystacks Is Not Hard with Neutrality , 2002, EuroGP.

[20]  Akin Ozcift,et al.  SVM Feature Selection Based Rotation Forest Ensemble Classifiers to Improve Computer-Aided Diagnosis of Parkinson Disease , 2012, Journal of medical systems.

[21]  Nawwaf N. Kharma,et al.  Advances in Detecting Parkinson's Disease , 2010, ICMB.

[22]  Mehmet Fatih Çağlar,et al.  Automatic Recognition of Parkinson's Disease from Sustained Phonation Tests Using ANN and Adaptive Neuro-Fuzzy Classifier , 2010 .

[23]  M. Hariharan,et al.  A new hybrid intelligent system for accurate detection of Parkinson's disease , 2014, Comput. Methods Programs Biomed..

[24]  Julian Francis Miller,et al.  Changing the Genospace: Solving GA Problems with Cartesian Genetic Programming , 2007, EuroGP.